Question

我已经根据本教程将LSTM示例放在一起： https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/

但是，本教程不可视化实际的数据点，而仅显示错误。这是我的所有数据，然后，当我尝试将训练和预测数据放在同一图上时会发生什么：

第二个简单地用：

plt.plot(yhat)
plt.plot(test_y)
plt.plot(train_y)

我知道这是由于数据的标准化导致的，但是我不确定是否有办法返回到类似于我的第一张图的内容，除了预测数据而不是历史数据。有没有办法改变我的时间戳独立变量以运行模型？理想情况下，我将可视化从训练到预测的时间价值。

（我还试图弄清楚如何用LSTM训练集进行预测，但这是一个非常不同的话题！）

完整代码在这里：

from math import sqrt
import numpy as np
from numpy import concatenate
from matplotlib import pyplot
import pandas as pd
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM

# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(data) is list else data.shape[1]
    df = DataFrame(data)
    cols, names = list(), list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
        names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
        if i == 0:
            names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
        else:
            names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
    # put it all together
    agg = concat(cols, axis=1)
    agg.columns = names
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg
# load dataset
dataset = read_csv('weeklyTrends-growthUnderlying.csv', header=0, index_col=0)
values = dataset.values
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# frame as supervised learning
reframed = series_to_supervised(scaled, 1, 1)

print(reframed.head())

# Visualize/plot data
%matplotlib inline
import matplotlib.pyplot as plt
# x = dataset['timestamp'].values
y = dataset['value'].values
plt.plot(y)
plt.show()

# split into train and test sets
# 26,207 observations
values = reframed.values
n_train = 13000
train = values[:n_train, :]
test = values[n_train:, :]
# split into input and outputs
train_X, train_y = train[:, :-1], train[:, -1]
test_X, test_y = test[:, :-1], test[:, -1]
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)

# design network
model = Sequential()
model.add(LSTM(32, return_sequences=True, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(LSTM(32))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=5, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)

# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()

# make a prediction
# change predict from (train_X) to range of test and future data
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], test_X.shape[2]))

plt.plot(yhat)
plt.plot(test_y)
plt.plot(train_y)

# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, 1:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, 1:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]

# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)

model.summary()

如何使用来自于Keras构建的LSTM模型的时间序列数据来可视化预测和训练数据？

0 个答案: